[Gluster-users] quick hadoop on gluster update

Jay Vyas jayunit100 at gmail.com
Fri Apr 11 21:54:02 UTC 2014


Hi gluster community !

- Brad childs has recently updated our glusterfs-hadoop plugin to support
multiple volumes, and its now available on our upstream release site:

http://rhbd.s3.amazonaws.com/maven/indexV2.html

We'd love to hear if any of you are hacking around with hadoop on gluster
what you think.  The basic implementation changes can be seen in the
core-site.xml file that the code ships with.
Some possibly ways you can use this multivolume mapreduce:

There are different performance and security use cases for this multivolume
hadoop accessible storage that we're excited about playi
ng with.

For example, if you have a "normal" volume with our suggested settings for
mapreduce jobs, keep it, and add in another volume for hadoop apps that do
high throughput writes or puts.  That way, your typical mapreduce jobs dont
suffer from eventual consistency, but you can still have HA where you need
it in your DFS.

-- 
Jay Vyas
http://jayunit100.blogspot.com
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://supercolony.gluster.org/pipermail/gluster-users/attachments/20140411/63fb404a/attachment.html>


More information about the Gluster-users mailing list